issues
search
jsphon
/
reinforcement_learning
Python Package For Reinforcement Learning
0
stars
0
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Create The Trainer Module
#51
jsphon
opened
6 years ago
0
Try Training in 2 steps
#50
jsphon
closed
6 years ago
0
Clean up the vectorizations
#49
jsphon
opened
6 years ago
0
Test the Learner module
#48
jsphon
opened
6 years ago
0
Tidy up line world example
#47
jsphon
opened
6 years ago
0
value_function improvements
#46
jsphon
closed
6 years ago
0
Write a test for QLearningActionTargetCalculator.vectorized
#45
jsphon
closed
6 years ago
0
Analyse Performance of the line world example
#44
jsphon
opened
6 years ago
0
Explore learning rate decay
#43
jsphon
opened
6 years ago
1
tf loop
#42
jsphon
opened
6 years ago
1
Adapting State Representations
#41
jsphon
closed
6 years ago
1
TODO
#40
jsphon
closed
6 years ago
0
Write some documentation
#39
jsphon
opened
7 years ago
0
Check the grid world works ok
#38
jsphon
closed
7 years ago
0
Move the ant world and rename it
#37
jsphon
closed
7 years ago
0
Refactor the State Machine States
#36
jsphon
closed
7 years ago
1
Should I fit the terminal state to have zero value?
#35
jsphon
closed
7 years ago
1
Should States be immutable?
#34
jsphon
closed
7 years ago
1
VectorizedStateMachineTargetArrayCalculator.
#33
jsphon
closed
7 years ago
1
Refactor the learning module
#32
jsphon
opened
7 years ago
0
Implement Reinforcement Learning for State Machines
#31
jsphon
closed
7 years ago
0
Move get_new_state
#30
jsphon
opened
7 years ago
0
Use Composition To Allow Vectorized and Scalar Learning
#29
jsphon
closed
7 years ago
0
Refactor Learner.learn
#28
jsphon
closed
7 years ago
0
Learner Tests Cleanup
#27
jsphon
closed
7 years ago
0
Cliff World Example Cleanup
#26
jsphon
closed
7 years ago
0
Fix Sarsa Mixing
#25
jsphon
closed
7 years ago
0
Implement some AI Gym Environments
#24
jsphon
opened
7 years ago
0
Cleanup the experience module.
#23
jsphon
closed
7 years ago
0
Implement the cliff walking grid world
#22
jsphon
closed
7 years ago
0
Fix Grid World's get action grid
#21
jsphon
closed
7 years ago
0
grid world example does not work with sarsa
#20
jsphon
closed
7 years ago
1
Learner.learn_episode / learn_episodes
#19
jsphon
closed
7 years ago
1
Implement the TD(lambda)
#18
jsphon
opened
7 years ago
0
Think About After States
#17
jsphon
closed
7 years ago
0
Double Learning
#16
jsphon
opened
7 years ago
1
Implement TD(0) for Page 133 random walk.
#15
jsphon
closed
7 years ago
0
Implement Monte Carlo for Blackjack
#14
jsphon
opened
7 years ago
0
Jacks Car rental
#13
jsphon
opened
7 years ago
0
Implement Policyxxx
#12
jsphon
opened
7 years ago
2
Experience Generator Class
#11
jsphon
closed
7 years ago
0
Create a learner function
#10
jsphon
closed
7 years ago
0
Investigate how much faster it is to use vectorised operations
#9
jsphon
closed
7 years ago
1
Refactor RLSystem
#8
jsphon
closed
7 years ago
0
Update generate_experience
#7
jsphon
closed
7 years ago
0
GridState has an apply_action method
#6
jsphon
closed
7 years ago
0
init grid function to randomize.
#5
jsphon
closed
7 years ago
0
Make a new example
#4
jsphon
closed
7 years ago
0
Update the generate experience function
#3
jsphon
closed
7 years ago
0
Make a more advance generate_experience function
#2
jsphon
closed
7 years ago
0
Next